MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Span is a local MCP server that keeps the semantic understanding your coding agent worked out — the conclusions, the exact evidence behind them, and what needs another look when that evidence changes. Three tools: ask, record, reconsider.
pypi Apache-2.0 ★ 1 -
iflow-mcp_rdondeti-codegrok-mcpgithub.com/rdondeti/codegrok_mcpupdated this year
MCP server for semantic code understanding and search
pypi MIT -
rpg-encodergithub.com/userFRM/rpg-encoderupdated this year
MCP server that gives AI coding agents semantic understanding of any codebase. Search by intent, auto-sync on edits, whole-repo context in one call. Rust + tree-sitter, 15 languages, 28 tools.
npm MIT ★ 33 -
Semantic understanding of JavaScript codebases for AI agents
npm MIT -
C++ Semantic Graph for AI — Build a code knowledge graph that lets AI assistants precisely understand your C++ codebase via MCP protocol
★ 3 -
The semantic layer for software engineering: Connect code to meaning, build on understanding
Apache-2.0 ★ 39 -
sqlserver-semantic-mcpgithub.com/lukedev999-boom/sqlserver-semantic-mcpupdated this year
Semantic intelligence layer for SQL Server databases, exposed via MCP. A database understanding engine for AI agents (Claude Code CLI, Codex CLI, Claude Desktop, etc.).
pypi MIT License -
Semantic code understanding for AI tools - One MCP Server for all AI coding assistants
npm MIT -
gotcontext-servergithub.com/oimiragieo/token-saver-5000updated this year
Self-hosted MCP server for gotcontext.ai — semantic compression, AST-aware code understanding, and context engineering for LLM agents.
pypi MIT -
AI-powered semantic search for Microsoft Dynamics 365 F&O development. Find and understand X++ code through natural language queries via Model Context Protocol (MCP).
NOASSERTION ★ 12 -
agent-browsergithub.com/atreasureboy/agent-browserupdated this year
Agent-readable semantic browser layer for AI agents — token-efficient web understanding, semantic snapshots, persistent sessions, and MCP/CLI/Python APIs.
MIT ★ 1 -
code-context-mcpgithub.com/RaheesAhmed/code-context-mcpupdated this year
The ultimate MCP server for code intelligence. Smart context, semantic search, call graphs, pattern detection & token optimization. Makes LLMs understand any codebase perfectly.
MIT -
sensegithub.com/luuuc/senseactive
MCP server for AI coding agents - gives Claude Code, OpenCode, Cursor, and Codex CLI structural understanding of your codebase: symbol graph, blast radius, semantic search, conventions.
go MIT ★ 47 -
mercury-cortexgithub.com/mercury-ai-1/mercury-cortexupdated this year
AI-powered developer knowledge engine with MCP, CLI, semantic code search, and contextual code understanding.
cargo Apache-2.0 -
yomugithub.com/thkt/yomuactive
Frontend-specialized semantic code search MCP server. Reads and understands your codebase. (読む)
Apache-2.0 ★ 1 -
Semantic code-search (semcode) MCP. Indexes code symbols and commit history. Combines dense embeddings with sparse BM25 vectors for hybrid search that balances semantic understanding with keyword precision.
MIT ★ 9 -
ciegithub.com/kraklabs/cieupdated this year
Code Intelligence Engine — indexes your codebase and gives AI assistants deep understanding via MCP (semantic search, call graphs, 20+ tools)
go AGPL-3.0 ★ 19 -
cntx-uigithub.com/nothingdao/cntx-uiupdated this year
Autonomous Repository Intelligence engine with web UI and MCP server. Unified semantic code understanding, local RAG, and agent working memory.
npm MIT -
AI Context Engineer: Intelligent MCP server that generates complete context packages for LLM coding tasks, with grep assistance and semantic understanding
npm MIT -
ultracodegithub.com/faxenoff/ultracodeupdated this year
Codebase RAG MCP server for code understanding - semantic search, duplicate detection, impact analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Kotlin/Swift/Zig/Bash
npm AGPL-3.0-only OR Commercial -
code-rag-mcpgithub.com/Mirrdhyn/code-rag-mcpupdated this year
MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
MIT ★ 5 -
@iflow-mcp/faxenoff-ultrascript-tools-mcpgithub.com/faxenoff/ultrascript-tools-mcpupdated this year
Codebase RAG MCP server for code understanding - semantic search, duplicate detection, impact analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Kotlin/Swift/Zig/Bash
npm MIT -
@iflow-mcp/duonglabs-mcp-codeintelgithub.com/duonglabs/mcp-codeintelupdated this year
A powerful MCP server for intelligent code analysis, semantic search, and structural understanding of codebases through AI-powered indexing and vector embeddings
npm MIT -
adaptive-transformer-search-mcpgithub.com/Particular-Audience/adaptive-transformer-search-mcpstale
MCP Server for Adaptive Transformer Search - AI-powered eCommerce product search using LLM semantic understanding to eliminate zero search results.
MIT ★ 5 -
Unity-MCP-Projectgithub.com/manasmuda/Unity-MCP-Projectupdated this year
A local MCP server that gives Claude deep contextual understanding of Unity projects via semantic search and structured queries. Python + Qdrant + FastMCP.
-
Local browser intelligence runtime with semantic memory, verified workflows, multi-surface understanding, CLI, TUI, MCP, and Rust APIs
cargo MIT -
CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, 38 languages, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files.
npm Apache-2.0 ★ 157 -
mugithub.com/0ximu/muactive
MCP server that gives AI assistants deep codebase understanding. Semantic graph, BM25 search, impact analysis, code review.
Apache-2.0 ★ 70 -
The most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations. Pre-indexed semantic knowledge graphs for instant code understanding — fewer tokens, fewer tool calls, 100% local.
mcpb MIT ★ 705 -
CodeGrok_mcpgithub.com/dondetir/CodeGrok_mcpupdated this year
CodeGrok MCP is a Model Context Protocol (MCP) server that enables AI assistants to intelligently search and understand codebases using semantic embeddings and Tree-sitter parsing.
NOASSERTION ★ 15 -
@wiseria/lucid-mcpgithub.com/wiseriaai/lucid-mcpupdated this year
AI-native data analysis agent as MCP Server. Connect Excel/CSV/MySQL/PostgreSQL, understand business semantics, query with natural language.
npm MIT -
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
go BSD-3-Clause ★ 60 -
knotgithub.com/raultov/knotactive
High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.
cargo MIT ★ 11 -
Advanced ADB MCP server for Android automation — optimised for small LLMs (gpt-oss-20b, qwen3vl). 15 semantic tools, OCR + Set-of-Mark dual-path screen understanding.
MIT ★ 2 -
A Rust-based Model Context Protocol (MCP) server that provides AI assistants with powerful RAG (Retrieval-Augmented Generation) capabilities for understanding massive codebases. Index codebases with FastEmbed + LanceDB, semantic code and git history searches with hybrid vector + BM25.
cargo MIT ★ 33 -
doc-syncgithub.com/engrmaziz/doc-syncupdated this year
Enterprise-grade documentation intelligence for AI coding assistants using the Model Context Protocol (MCP). Index, synchronize, understand, and retrieve documentation from any source with blazing-fast semantic search and developer-friendly workflows.
MIT -
SwiftLens is a Model Context Protocol (MCP) server that provides deep, semantic-level analysis of Swift codebases to any AI models. By integrating directly with Apple's SourceKit-LSP, SwiftLens enables AI models to understand Swift code with compiler-grade accuracy.
pypi Proprietary -
narragithub.com/florinutz/narraupdated this year
Narrative intelligence engine for AI. An MCP server and CLI that manages characters, relationships, knowledge, and story events with semantic embeddings, arc tracking, and perspective vectors. Gives AI assistants deep, queryable understanding of complex narrative worlds. Built with Rust, SurrealDB, and FastEmbed.
MIT ★ 5 -
cwm.roslynnavigatorgithub.com/codewithmukesh/dotnet-claude-kitupdated this year
A Model Context Protocol (MCP) server that gives AI coding assistants semantic understanding of .NET codebases via Roslyn. 20 read-only tools for symbol navigation, reference finding, type hierarchy, dependency graphs, anti-pattern detection, dead code analysis, diagnostics, file outlines, symbol source extraction, NuGet package inventory, endpoint maps, and DI registration analysis — all returning token-optimized responses. Part of the dotnet-claude-kit ecosystem.
nuget MIT -
pieces-to-mem0github.com/mango766/pieces-to-mem0updated this year
Pieces-to-Mem0 is a LLM-powered personal memory connector — auto-distills Pieces OS screen activities into semantic memories stored in Mem0, accessible via MCP in Cursor/Claude Desktop. Make your AI truly understand you.
★ 1 -
VSC-MCPServergithub.com/CodingWithCalvin/VSC-MCPServerupdated this year
A Visual Studio Code extension that exposes an MCP (Model Context Protocol) server, giving AI tools like Claude, Cursor, and others direct access to VS Code's semantic code understanding capabilities - go-to-definition, find references, completions, diagnostics, and so much more!
MIT -
PeopleMesh is the AI-powered matching layer for modern organizations. It helps people discover the right colleagues, internal opportunities, communities, and projects through semantic search that understands context, not just keywords.
Apache-2.0 ★ 12 -
codexraygithub.com/iohub/codexrayupdated this year
A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine, both supports claude code and codex
MIT ★ 52 -
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.
npm Apache-2.0 ★ 524 -
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
pypi MIT ★ 37 -
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
npm NOASSERTION ★ 68 -
A multi-agent NLP system that analyzes, summarizes, and compares insurance policy documents. It enables intelligent document understanding, semantic search, and comparative analysis between Tunisian and international insurance standards
-
docwisegithub.com/rakmohan/docwiseupdated this year
RAG-in-a-Box — intelligent document understanding for PDF, DOCX, and Markdown. Adaptive parsing, hybrid search (semantic + BM25), and agentic Q&A with citations. Upload, ask questions, and explore stats via built-in Streamlit app, REST API, or Claude Desktop (MCP).
-
Roslyn-based MCP server giving AI agents deep semantic understanding of .NET/C# codebases — 67 tools for navigation, call graphs, diagnostics & code fixes, safe refactoring, code-quality auditing, test intelligence, DI graphs, and IL/external-assembly inspection.
nuget MIT ★ 74 -
Code intelligence MCP server for AI coding agents. AST-level codebase understanding — semantic search, symbol navigation, real reference graphs, and cross-language bridge detection across many languages. Local-first; works with any MCP client (Claude Code, Cursor, Copilot).
MIT ★ 4 -
dooragithub.com/backpack-lab/dooraupdated this year
Doora parses source files into syntax trees and runs S-expression queries to find functions, types, and call sites that grep misses. Supports Rust, Python, JS, TS, Go, C, and C++. Exposes an MCP server so AI agents understand your codebase semantically, cutting hallucinations and wasted context tokens.
Apache-2.0 ★ 10 -
@smallthinkingmachines/semantic-code-mcpgithub.com/smallthinkingmachines/semantic-code-mcpupdated this year
MCP server for semantic code search using AST-aware chunking and vector embeddings
npm MIT -
videoseek-mcpgithub.com/kennyzheng-builds/videoseek-mcpupdated this year
VideoSeek MCP — Find anything in any video. Semantic video search, video Q&A, persistent memory, and social media import for AI agents.
★ 2 -
An end-to-end AI-powered relevance and visual content-matching engine with MCP and RAG capabilities, designed to evaluate, rank, and pair imagery with textual context using multimodal embeddings and deep visual-semantic scoring
AGPL-3.0 ★ 1 -
@mars167/git-aigithub.com/mars167/git-ai-cliupdated this year
A git-compatible CLI with AI indexing/search and an MCP server.
npm MIT -
sivrugithub.com/sivru/sivruupdated this year
Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli
npm MIT ★ 4 -
Bizy is the first rules and logic layer that machines, engineers and business stakeholders can directly configure and understand.
MIT ★ 3 -
MCP server that helps AI understand coding missions - know what you're building before you build it
npm MIT -
An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.
oci AGPL-3.0 ★ 1,096